PxA Labs. An independent research collective from India building open, measurable intelligent systems, from safety monitors for fine-tuned LLMs and accent-robust speech recognition to interpretable genomics and real-time adaptive optics. Every result is reported against a fair baseline, including what did not work.
| Project | On the Hub |
|---|---|
| SafetyPulse: catches safety drift during fine-tuning, repairs it, audits the repair | Models: tiny-aya-global-safetypulse-repaired · NF4 4-bit · LoRA adapters (alpaca, alpacacur, gsm8k, none) Datasets: eval · finetune-data · pairs · probe-bundle · logs |
| IndiVoice-DeepASR: Whisper + LoRA for Indian-accented speech | Model: whisper-indian-lora |
| AutoMaintainer: an always-on autonomous AI software engineering team | Space: AutoMaintainer |
Code for every project is on GitHub.
Website · GitHub · LinkedIn · Instagram · Discord · pxalabs@gmail.com